Uses of Class
org.tribuo.Model
Packages that use Model
Package
Description
Provides the core interfaces and classes for using Tribuo.
Evaluation classes for anomaly detection.
Provides an interface to LibSVM for anomaly detection problems.
Provides classes and infrastructure for multiclass classification problems.
Provides simple baseline multiclass classifiers.
Provides majority vote ensemble combiners for classification
along with an implementation of multiclass Adaboost.
Evaluation classes for multi-class classification.
Provides a set of main methods for interacting with classification tasks.
Provides core infrastructure for local model based explanations.
Provides an implementation of LIME (Locally Interpretable Model Explanations).
Provides an interface to LibLinear-java for classification problems.
Provides an interface to LibSVM for classification problems.
Provides an implementation of multinomial naive bayes (i.e., naive bayes for non-negative count data).
Provides a SGD implementation of a Kernel SVM using the Pegasos algorithm.
Provides an implementation of a classification linear model using Stochastic Gradient Descent.
Evaluation classes for clustering.
Provides a multithreaded implementation of K-Means, with a
configurable distance function.
Provides base classes for using liblinear from Tribuo.
The base interface to LibSVM.
Provides a K-Nearest Neighbours implementation which works across
all Tribuo
Output
types.Provides common functionality for building decision trees, irrespective
of the predicted
Output
.Provides abstract classes for interfacing with XGBoost abstracting away all the
Output
dependent parts.Provides classes for loading in data from disk, processing it into examples, and splitting datasets for
things like cross-validation and train-test splits.
Provides classes for processing columnar data and generating
Example
s.Provides an interface for model prediction combinations,
two base classes for ensemble models, a base class for
ensemble excuses, and a Bagging implementation.
Evaluation base classes, along with code for train/test splits and cross validation.
This package contains the infrastructure classes for building evaluation metrics.
Provides the base interface and implementations of the
Model
hashing
which obscures the feature names stored in a model.This package contains the abstract implementation of an external model
trained by something outside of Tribuo.
This package contains a Tribuo wrapper around the ONNX Runtime.
Provides an interface to Tensorflow, allowing the training of non-sequential models using any supported
Tribuo output type.
Evaluation classes for multi-label classification using
MultiLabel
.Provides simple baseline regression predictors.
Evaluation classes for single or multi-dimensional regression.
Provides an interface to liblinear for regression problems.
Provides an interface to LibSVM for regression problems.
Provides an implementation of decision trees for regression problems.
Provides an implementation of linear regression using Stochastic Gradient Descent.
Provides implementations of sparse linear regression using various forms of regularisation penalty.
Provides infrastructure for applying transformations to a
Dataset
.-
Uses of Model in org.tribuo
Classes in org.tribuo with type parameters of type ModelModifier and TypeInterfaceDescriptioninterface
IncrementalTrainer<T extends Output<T>, U extends Model<T>>
An interface for incremental training ofModel
s.Subclasses of Model in org.tribuoModifier and TypeClassDescriptionclass
SparseModel<T extends Output<T>>
A model which uses a subset of the features it knows about to make predictions.Methods in org.tribuo that return ModelModifier and TypeMethodDescriptionModel.copy()
Copies a model, returning a deep copy of any mutable state, and a shallow copy otherwise.Model.copy
(String newName, ModelProvenance newProvenance) Copies a model, replacing it's provenance and name with the supplied values.Trains a predictive model using the examples in the given data set.Trainer.train
(Dataset<T> examples, Map<String, com.oracle.labs.mlrg.olcut.provenance.Provenance> runProvenance) Trains a predictive model using the examples in the given data set.Constructors in org.tribuo with parameters of type ModelModifierConstructorDescriptionImmutableDataset
(DataSource<T> dataSource, Model<T> model, boolean dropInvalidExamples) Creates a dataset from a data source. -
Uses of Model in org.tribuo.anomaly.evaluation
Methods in org.tribuo.anomaly.evaluation with parameters of type ModelModifier and TypeMethodDescriptionprotected org.tribuo.anomaly.evaluation.AnomalyMetric.Context
AnomalyEvaluator.createContext
(Model<Event> model, List<Prediction<Event>> predictions) org.tribuo.anomaly.evaluation.AnomalyMetric.Context
AnomalyMetric.createContext
(Model<Event> model, List<Prediction<Event>> predictions) protected Set
<AnomalyMetric> AnomalyEvaluator.createMetrics
(Model<Event> model) -
Uses of Model in org.tribuo.anomaly.libsvm
Subclasses of Model in org.tribuo.anomaly.libsvmModifier and TypeClassDescriptionclass
A anomaly detection model that uses an underlying libSVM model to make the predictions. -
Uses of Model in org.tribuo.classification
Methods in org.tribuo.classification that return Model -
Uses of Model in org.tribuo.classification.baseline
Subclasses of Model in org.tribuo.classification.baselineModifier and TypeClassDescriptionclass
A model which performs dummy classifications (e.g., constant output, uniform sampled labels, stratified sampled labels).Methods in org.tribuo.classification.baseline that return Model -
Uses of Model in org.tribuo.classification.ensemble
Methods in org.tribuo.classification.ensemble that return Model -
Uses of Model in org.tribuo.classification.evaluation
Methods in org.tribuo.classification.evaluation with parameters of type ModelModifier and TypeMethodDescriptionprotected LabelMetric.Context
LabelEvaluator.createContext
(Model<Label> model, List<Prediction<Label>> predictions) LabelMetric.createContext
(Model<Label> model, List<Prediction<Label>> predictions) protected Set
<LabelMetric> LabelEvaluator.createMetrics
(Model<Label> model) Constructors in org.tribuo.classification.evaluation with parameters of type ModelModifierConstructorDescriptionLabelConfusionMatrix
(Model<Label> model, List<Prediction<Label>> predictions) Creates a confusion matrix from the supplied predictions, using the label info from the supplied model. -
Uses of Model in org.tribuo.classification.experiments
Methods in org.tribuo.classification.experiments that return types with arguments of type Model -
Uses of Model in org.tribuo.classification.explanations
Methods in org.tribuo.classification.explanations that return Model -
Uses of Model in org.tribuo.classification.explanations.lime
Fields in org.tribuo.classification.explanations.lime declared as ModelConstructors in org.tribuo.classification.explanations.lime with parameters of type ModelModifierConstructorDescriptionLIMEBase
(SplittableRandom rng, Model<Label> innerModel, SparseTrainer<Regressor> explanationTrainer, int numSamples) Constructs a LIME explainer for a model which uses tabular data (i.e., no special treatment for text features).LIMEColumnar
(SplittableRandom rng, Model<Label> innerModel, SparseTrainer<Regressor> explanationTrainer, int numSamples, RowProcessor<Label> exampleGenerator, Tokenizer tokenizer) Constructs a LIME explainer for a model which uses the columnar data processing system.LIMEText
(SplittableRandom rng, Model<Label> innerModel, SparseTrainer<Regressor> explanationTrainer, int numSamples, TextFeatureExtractor<Label> extractor, Tokenizer tokenizer) Constructs a LIME explainer for a model which uses text data. -
Uses of Model in org.tribuo.classification.liblinear
Subclasses of Model in org.tribuo.classification.liblinearModifier and TypeClassDescriptionclass
AModel
which wraps a LibLinear-java classification model. -
Uses of Model in org.tribuo.classification.libsvm
Subclasses of Model in org.tribuo.classification.libsvmModifier and TypeClassDescriptionclass
A classification model that uses an underlying LibSVM model to make the predictions. -
Uses of Model in org.tribuo.classification.mnb
Subclasses of Model in org.tribuo.classification.mnbModifier and TypeClassDescriptionclass
AModel
for multinomial Naive Bayes with Laplace smoothing.Methods in org.tribuo.classification.mnb that return Model -
Uses of Model in org.tribuo.classification.sgd.kernel
Subclasses of Model in org.tribuo.classification.sgd.kernelModifier and TypeClassDescriptionclass
The inference time version of a kernel model trained using Pegasos. -
Uses of Model in org.tribuo.classification.sgd.linear
Subclasses of Model in org.tribuo.classification.sgd.linearModifier and TypeClassDescriptionclass
The inference time version of a linear model trained using SGD.Methods in org.tribuo.classification.sgd.linear that return Model -
Uses of Model in org.tribuo.clustering.evaluation
Methods in org.tribuo.clustering.evaluation with parameters of type ModelModifier and TypeMethodDescriptionprotected org.tribuo.clustering.evaluation.ClusteringMetric.Context
ClusteringEvaluator.createContext
(Model<ClusterID> model, List<Prediction<ClusterID>> predictions) org.tribuo.clustering.evaluation.ClusteringMetric.Context
ClusteringMetric.createContext
(Model<ClusterID> model, List<Prediction<ClusterID>> predictions) protected Set
<ClusteringMetric> ClusteringEvaluator.createMetrics
(Model<ClusterID> model) -
Uses of Model in org.tribuo.clustering.kmeans
Subclasses of Model in org.tribuo.clustering.kmeansModifier and TypeClassDescriptionclass
A K-Means model with a selectable distance function. -
Uses of Model in org.tribuo.common.liblinear
Subclasses of Model in org.tribuo.common.liblinearModifier and TypeClassDescriptionclass
LibLinearModel<T extends Output<T>>
AModel
which wraps a LibLinear-java model. -
Uses of Model in org.tribuo.common.libsvm
Subclasses of Model in org.tribuo.common.libsvmModifier and TypeClassDescriptionclass
LibSVMModel<T extends Output<T>>
A model that uses an underlying libSVM model to make the predictions. -
Uses of Model in org.tribuo.common.nearest
Subclasses of Model in org.tribuo.common.nearestModifier and TypeClassDescriptionclass
A k-nearest neighbours model.Methods in org.tribuo.common.nearest that return Model -
Uses of Model in org.tribuo.common.tree
Subclasses of Model in org.tribuo.common.tree -
Uses of Model in org.tribuo.common.xgboost
Subclasses of Model in org.tribuo.common.xgboostModifier and TypeClassDescriptionfinal class
XGBoostExternalModel<T extends Output<T>>
AModel
which wraps around a XGBoost.Booster which was trained by a system other than Tribuo.final class
XGBoostModel<T extends Output<T>>
AModel
which wraps around a XGBoost.Booster.Methods in org.tribuo.common.xgboost that return ModelModifier and TypeMethodDescriptionXGBoostModel.copy
(String newName, ModelProvenance newProvenance) -
Uses of Model in org.tribuo.data
Methods in org.tribuo.data with parameters of type Model -
Uses of Model in org.tribuo.data.columnar
Methods in org.tribuo.data.columnar with parameters of type ModelModifier and TypeMethodDescriptionvoid
RowProcessor.expandRegexMapping
(Model<T> model) Uses similar logic toTransformationMap.validateTransformations(org.tribuo.FeatureMap)
to check the regexes against theImmutableFeatureMap
contained in the suppliedModel
. -
Uses of Model in org.tribuo.ensemble
Subclasses of Model in org.tribuo.ensembleModifier and TypeClassDescriptionclass
EnsembleModel<T extends Output<T>>
A model which contains a list of otherModel
s.final class
WeightedEnsembleModel<T extends Output<T>>
An ensemble model that uses weights to combine the ensemble member predictions.Fields in org.tribuo.ensemble with type parameters of type ModelMethods in org.tribuo.ensemble that return ModelModifier and TypeMethodDescriptionEnsembleModel.copy
(String name, ModelProvenance newProvenance) BaggingTrainer.train
(Dataset<T> examples, Map<String, com.oracle.labs.mlrg.olcut.provenance.Provenance> runProvenance) BaggingTrainer.trainSingleModel
(Dataset<T> examples, ImmutableFeatureMap featureIDs, ImmutableOutputInfo<T> labelIDs, SplittableRandom localRNG, Map<String, com.oracle.labs.mlrg.olcut.provenance.Provenance> runProvenance) Methods in org.tribuo.ensemble that return types with arguments of type ModelModifier and TypeMethodDescriptionEnsembleModel.getModels()
Returns an unmodifiable view on the ensemble members.Method parameters in org.tribuo.ensemble with type arguments of type ModelModifier and TypeMethodDescriptionprotected abstract EnsembleModel
<T> protected EnsembleModel
<T> WeightedEnsembleModel.copy
(String name, EnsembleModelProvenance newProvenance, List<Model<T>> newModels) Constructor parameters in org.tribuo.ensemble with type arguments of type ModelModifierConstructorDescriptionEnsembleModel
(String name, EnsembleModelProvenance description, ImmutableFeatureMap featureIDMap, ImmutableOutputInfo<T> outputIDInfo, List<Model<T>> newModels) WeightedEnsembleModel
(String name, EnsembleModelProvenance description, ImmutableFeatureMap featureIDMap, ImmutableOutputInfo<T> outputIDInfo, List<Model<T>> newModels, EnsembleCombiner<T> combiner) WeightedEnsembleModel
(String name, EnsembleModelProvenance description, ImmutableFeatureMap featureIDMap, ImmutableOutputInfo<T> outputIDInfo, List<Model<T>> newModels, EnsembleCombiner<T> combiner, float[] weights) -
Uses of Model in org.tribuo.evaluation
Methods in org.tribuo.evaluation that return types with arguments of type ModelModifier and TypeMethodDescriptionCrossValidation.evaluate()
Performs k fold cross validation, returning the k evaluations.Methods in org.tribuo.evaluation with parameters of type ModelModifier and TypeMethodDescriptionstatic <T extends Output<T>, C extends MetricContext<T>>
com.oracle.labs.mlrg.olcut.util.Pair<Integer, Double> EvaluationAggregator.argmax
(EvaluationMetric<T, C> metric, Model<T> model, List<? extends Dataset<T>> datasets) Calculates the argmax of a metric across the supplied datasets.protected abstract C
AbstractEvaluator.createContext
(Model<T> model, List<Prediction<T>> predictions) Create the context needed for evaluation.AbstractEvaluator.createMetrics
(Model<T> model) Creates the appropriate set of metrics for this model, by querying for it'sOutputInfo
.default OnlineEvaluator
<T, E> Evaluator.createOnlineEvaluator
(Model<T> model, DataProvenance provenance) Creates an online evaluator that maintains a list of all the predictions it has seen and can evaluate them upon request.final E
AbstractEvaluator.evaluate
(Model<T> model, List<Prediction<T>> predictions, DataProvenance dataProvenance) Produces an evaluation for the supplied model and predictions by aggregating the appropriate statistics.final E
Produces an evaluation for the supplied model and dataset, by callingpredict(org.tribuo.Example<T>)
to create the predictions, then aggregating the appropriate statistics.final E
AbstractEvaluator.evaluate
(Model<T> model, DataSource<T> datasource) Produces an evaluation for the supplied model and datasource, by callingpredict(org.tribuo.Example<T>)
to create the predictions, then aggregating the appropriate statistics.default E
Evaluator.evaluate
(Model<T> model, List<Prediction<T>> predictions, List<T> groundTruth, DataProvenance dataProvenance) Evaluates the model performance using the supplied predictions, returning an immutableEvaluation
of the appropriate type.Evaluator.evaluate
(Model<T> model, List<Prediction<T>> predictions, DataProvenance dataProvenance) Evaluates the model performance using the supplied predictions, returning an immutableEvaluation
of the appropriate type.Evaluates the dataset using the supplied model, returning an immutableEvaluation
of the appropriate type.Evaluator.evaluate
(Model<T> model, DataSource<T> datasource) Evaluates the dataset using the supplied model, returning an immutableEvaluation
of the appropriate type.static <T extends Output<T>, C extends MetricContext<T>>
DescriptiveStatsEvaluationAggregator.summarize
(List<? extends EvaluationMetric<T, C>> metrics, Model<T> model, List<Prediction<T>> predictions) Summarize model performance on dataset across several metrics.static <T extends Output<T>, C extends MetricContext<T>>
DescriptiveStatsEvaluationAggregator.summarize
(List<? extends EvaluationMetric<T, C>> metrics, Model<T> model, Dataset<T> dataset) Summarize model performance on dataset across several metrics.static <T extends Output<T>, R extends Evaluation<T>>
Map<MetricID<T>, DescriptiveStats> EvaluationAggregator.summarize
(Evaluator<T, R> evaluator, Model<T> model, List<? extends Dataset<T>> datasets) Summarize performance according to evaluator for a single model across several datasets.static <T extends Output<T>, C extends MetricContext<T>>
DescriptiveStatsEvaluationAggregator.summarize
(EvaluationMetric<T, C> metric, Model<T> model, List<? extends Dataset<T>> datasets) Summarize a model's performance w.r.t.Method parameters in org.tribuo.evaluation with type arguments of type ModelModifier and TypeMethodDescriptionstatic <T extends Output<T>, C extends MetricContext<T>>
com.oracle.labs.mlrg.olcut.util.Pair<Integer, Double> EvaluationAggregator.argmax
(EvaluationMetric<T, C> metric, List<? extends Model<T>> models, Dataset<T> dataset) Calculates the argmax of a metric across the supplied models (i.e., the index of the model which performed the best).static <T extends Output<T>, R extends Evaluation<T>>
Map<MetricID<T>, DescriptiveStats> EvaluationAggregator.summarize
(Evaluator<T, R> evaluator, List<? extends Model<T>> models, Dataset<T> dataset) Summarize performance using the supplied evaluator across several models on one dataset.static <T extends Output<T>, C extends MetricContext<T>>
DescriptiveStatsEvaluationAggregator.summarize
(EvaluationMetric<T, C> metric, List<? extends Model<T>> models, Dataset<T> dataset) Summarize performance w.r.t.Constructors in org.tribuo.evaluation with parameters of type ModelModifierConstructorDescriptionOnlineEvaluator
(Evaluator<T, E> evaluator, Model<T> model, DataProvenance provenance) Constructs anOnlineEvaluator
which accumulates predictions. -
Uses of Model in org.tribuo.evaluation.metrics
Methods in org.tribuo.evaluation.metrics that return ModelMethods in org.tribuo.evaluation.metrics with parameters of type ModelModifier and TypeMethodDescriptionEvaluationMetric.createContext
(Model<T> model, List<Prediction<T>> predictions) Creates the context this metric uses to compute it's value.default C
EvaluationMetric.createContext
(Model<T> model, Dataset<T> dataset) Creates the metric context used to compute this metric's value, generatingPrediction
s for eachExample
in the supplied dataset.Constructors in org.tribuo.evaluation.metrics with parameters of type ModelModifierConstructorDescriptionprotected
MetricContext
(Model<T> model, List<Prediction<T>> predictions) -
Uses of Model in org.tribuo.hash
Methods in org.tribuo.hash that return Model -
Uses of Model in org.tribuo.interop
Subclasses of Model in org.tribuo.interopModifier and TypeClassDescriptionclass
ExternalModel<T extends Output<T>, U, V>
This is the base class for third party models which are trained externally and loaded into Tribuo for prediction. -
Uses of Model in org.tribuo.interop.onnx
Subclasses of Model in org.tribuo.interop.onnxModifier and TypeClassDescriptionfinal class
ONNXExternalModel<T extends Output<T>>
A Tribuo wrapper around a ONNX model.Methods in org.tribuo.interop.onnx that return ModelModifier and TypeMethodDescriptionONNXExternalModel.copy
(String newName, ModelProvenance newProvenance) -
Uses of Model in org.tribuo.interop.tensorflow
Subclasses of Model in org.tribuo.interop.tensorflowModifier and TypeClassDescriptionclass
TensorflowCheckpointModel<T extends Output<T>>
TensorFlow support is experimental, and may change without a major version bump.final class
TensorflowExternalModel<T extends Output<T>>
A Tribuo wrapper around a Tensorflow frozen model.class
TensorflowModel<T extends Output<T>>
This model encapsulates a simple model with a single input tensor (labelledTensorflowModel.INPUT_NAME
), and produces a single output tensor (labelledTensorflowModel.OUTPUT_NAME
).Methods in org.tribuo.interop.tensorflow that return ModelModifier and TypeMethodDescriptionTensorflowExternalModel.copy
(String newName, ModelProvenance newProvenance) TensorflowCheckpointTrainer.train
(Dataset<T> examples, Map<String, com.oracle.labs.mlrg.olcut.provenance.Provenance> runProvenance) TensorflowTrainer.train
(Dataset<T> examples, Map<String, com.oracle.labs.mlrg.olcut.provenance.Provenance> runProvenance) Methods in org.tribuo.interop.tensorflow with parameters of type Model -
Uses of Model in org.tribuo.multilabel.baseline
Subclasses of Model in org.tribuo.multilabel.baselineModifier and TypeClassDescriptionclass
AModel
which wraps n binary models, where n is the size of the MultiLabel domain.Methods in org.tribuo.multilabel.baseline that return ModelModifier and TypeMethodDescriptionIndependentMultiLabelTrainer.train
(Dataset<MultiLabel> examples, Map<String, com.oracle.labs.mlrg.olcut.provenance.Provenance> runProvenance) -
Uses of Model in org.tribuo.multilabel.evaluation
Methods in org.tribuo.multilabel.evaluation with parameters of type ModelModifier and TypeMethodDescriptionprotected org.tribuo.multilabel.evaluation.MultiLabelMetric.Context
MultiLabelEvaluator.createContext
(Model<MultiLabel> model, List<Prediction<MultiLabel>> predictions) org.tribuo.multilabel.evaluation.MultiLabelMetric.Context
MultiLabelMetric.createContext
(Model<MultiLabel> model, List<Prediction<MultiLabel>> predictions) protected Set
<MultiLabelMetric> MultiLabelEvaluator.createMetrics
(Model<MultiLabel> model) Constructors in org.tribuo.multilabel.evaluation with parameters of type ModelModifierConstructorDescriptionMultiLabelConfusionMatrix
(Model<MultiLabel> model, List<Prediction<MultiLabel>> predictions) -
Uses of Model in org.tribuo.regression.baseline
Subclasses of Model in org.tribuo.regression.baselineModifier and TypeClassDescriptionclass
A model which performs dummy regressions (e.g., constant output, gaussian sampled output, mean value, median, quartile).Methods in org.tribuo.regression.baseline that return ModelModifier and TypeMethodDescriptionDummyRegressionModel.copy
(String newName, ModelProvenance newProvenance) -
Uses of Model in org.tribuo.regression.evaluation
Methods in org.tribuo.regression.evaluation with parameters of type ModelModifier and TypeMethodDescriptionprotected org.tribuo.regression.evaluation.RegressionMetric.Context
RegressionEvaluator.createContext
(Model<Regressor> model, List<Prediction<Regressor>> predictions) org.tribuo.regression.evaluation.RegressionMetric.Context
RegressionMetric.createContext
(Model<Regressor> model, List<Prediction<Regressor>> predictions) protected Set
<RegressionMetric> RegressionEvaluator.createMetrics
(Model<Regressor> model) -
Uses of Model in org.tribuo.regression.impl
Subclasses of Model in org.tribuo.regression.implModifier and TypeClassDescriptionclass
AModel
which wraps n independent regression models, where n is the size of the MultipleRegressor domain.class
ASparseModel
which wraps n independent regression models, where n is the size of the MultipleRegressor domain. -
Uses of Model in org.tribuo.regression.liblinear
Subclasses of Model in org.tribuo.regression.liblinear -
Uses of Model in org.tribuo.regression.libsvm
Subclasses of Model in org.tribuo.regression.libsvmModifier and TypeClassDescriptionclass
A regression model that uses an underlying libSVM model to make the predictions. -
Uses of Model in org.tribuo.regression.rtree
Subclasses of Model in org.tribuo.regression.rtreeModifier and TypeClassDescriptionfinal class
-
Uses of Model in org.tribuo.regression.sgd.linear
Subclasses of Model in org.tribuo.regression.sgd.linearModifier and TypeClassDescriptionclass
The inference time version of a linear model trained using SGD. -
Uses of Model in org.tribuo.regression.slm
Subclasses of Model in org.tribuo.regression.slmModifier and TypeClassDescriptionclass
The inference time version of a sparse linear regression model.Methods in org.tribuo.regression.slm that return ModelModifier and TypeMethodDescriptionSparseLinearModel.copy
(String newName, ModelProvenance newProvenance) -
Uses of Model in org.tribuo.transform
Subclasses of Model in org.tribuo.transformModifier and TypeClassDescriptionclass
TransformedModel<T extends Output<T>>
Wraps aModel
with it'sTransformerMap
so allExample
s are transformed appropriately before the model makes predictions.